GitLab

* Print python code

Implements the operator==(dynamic_dimension, size_t) functions

HIP had change in previous rocm releases to use --offload-arch instead of --cuda-gpu-arch.

This should be backwards compatbile. hipRTC also supports --offload-arch.

The operator-(size_t ,dyn_dim) is not used and somewhat bug prone

Extends dot MIGX operator to handle dynamic input shapes
Only allow dot between two dynamic shapes that have exactly matching outer dimensions
Inner dimensions must also match correspondingly
Updates dot related tests
Change check_shapes to use shape.ndim()
ONNX parsers for GEMM and MatMult will be updated in a separate PR

No major changes required, use dyn_output and pass dynamic shape when calling compute_shape()
Adds dynamic shape tests

Merge branch 'refactor_dyn_fixed_compare' of github.com:ROCmSoftwarePlatform/AMDMIGraphX into dyn_pad

Changes flatten's compute_shape() to handle dynamic shapes
Calculates the flattened shape with the min, max, and opt

Currently, quantizing a program with rnn layers to fp16 results in segmentation faults due to a "convert" operation being applied to an "undefined" instruction.

The following changes are implemented to fix this issue:

Added is_undefined method to the instruction class that returns true if all inputs to the instruction are from an undefined op.
Updated rewrite_rnn pass to use the new is_undefined method rather than checking ins->name()
Updated the dead_code_elimination pass to also use this new method rather than only checking the instruction name

* Add implicit_conversion

Misc. style changes.  Added a shape test and an onnx test for the case of reduce op. with no axes specified (should reduce all axes).  The new Onnx test case is stll under construction and doesn't pass.

Extends the Argmax operator to handle dynamic input shapes.
Only shape function changes